Decentralized Mean Field Games
Sriram Ganapathi Subramanian, Matthew E. Taylor, Mark Crowley, Pascal, Poupart

TL;DR
This paper introduces Decentralized Mean Field Games, allowing heterogeneous agents to learn independently in large-scale multiagent environments, with theoretical guarantees and practical applications including ride-sharing.
Contribution
It relaxes the assumption of agent indistinguishability in mean field theory, enabling decentralized learning among diverse agents with theoretical and empirical validation.
Findings
Decentralized mean field algorithms outperform baselines.
Applicable to heterogeneous and large-scale environments.
Successfully applied to real-world ride-sharing data.
Abstract
Multiagent reinforcement learning algorithms have not been widely adopted in large scale environments with many agents as they often scale poorly with the number of agents. Using mean field theory to aggregate agents has been proposed as a solution to this problem. However, almost all previous methods in this area make a strong assumption of a centralized system where all the agents in the environment learn the same policy and are effectively indistinguishable from each other. In this paper, we relax this assumption about indistinguishable agents and propose a new mean field system known as Decentralized Mean Field Games, where each agent can be quite different from others. All agents learn independent policies in a decentralized fashion, based on their local observations. We define a theoretical solution concept for this system and provide a fixed point guarantee for a Q-learning based…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAuction Theory and Applications · Experimental Behavioral Economics Studies · Supply Chain and Inventory Management
